tf.compat.v1.layers.AveragePooling3D

Average pooling layer for 3D inputs (e.g. volumes).

Inherits From: AveragePooling3D, Layer, Layer, Module

tf.compat.v1.layers.AveragePooling3D(
    pool_size,
    strides,
    padding='valid',
    data_format='channels_last',
    name=None,
    **kwargs
)

Migrate to TF2

This API is a legacy api that is only compatible with eager execution and tf.function if you combine it with tf.compat.v1.keras.utils.track_tf1_style_variables

Please refer to tf.layers model mapping section of the migration guide to learn how to use your TensorFlow v1 model in TF2 with Keras.

The corresponding TensorFlow v2 layer is tf.keras.layers.AveragePooling3D.

Structural Mapping to Native TF2

None of the supported arguments have changed name.

Before:

 pooling = tf.compat.v1.layers.AveragePooling3D(pool_size=2, strides=2)

After:

 pooling = tf.keras.layers.AveragePooling3D(pool_size=2, strides=2)

Description

pool_size An integer or tuple/list of 3 integers: (pool_depth, pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions.
strides An integer or tuple/list of 3 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions.
padding A string. The padding method, either 'valid' or 'same'. Case-insensitive.
data_format A string. The ordering of the dimensions in the inputs. channels_last (default) and channels_first are supported. channels_last corresponds to inputs with shape (batch, depth, height, width, channels) while channels_first corresponds to inputs with shape (batch, channels, depth, height, width).
name A string, the name of the layer.

graph

scope_name